© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 106252
    Prev
    Next
    INDEX
    Explanations

    punctuated dialogue and quotation marks in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bakan
    -0.09
    ì£
    -0.09
    nga
    -0.09
     disap
    -0.09
    [image
    -0.09
    hend
    -0.08
    ddb
    -0.08
    ãĥ³ãĥIJ
    -0.08
    ủ
    -0.08
    ë¨
    -0.08
    POSITIVE LOGITS
     I
    0.06
     in
    0.06
     about
    0.05
     E
    0.05
     Owens
    0.05
     ,
    0.05
    ucas
    0.05
     between
    0.05
     Cas
    0.05
    ket
    0.05
    Activations Density 0.001%

    No Known Activations